Updte notebook

Author: matanbt

quickstart.ipynb

@@ -105,9 +105,9 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/home/sharifm/students/matanbentov/my_conda/envs/default/lib/python3.10/site-packages/pydantic/_internal/_generate_schema.py:2249: UnsupportedFieldAttributeWarning: The 'repr' attribute with value False was provided to the `Field()` function, which has no effect in the context it was used. 'repr' is field-specific metadata, and can only be attached to a model field using `Annotated` metadata or by assignment. This may have happened because an `Annotated` type alias using the `type` statement was used, or if the `Field()` function was attached to a single member of a union type.\n",
+      ".../site-packages/pydantic/_internal/_generate_schema.py:2249: UnsupportedFieldAttributeWarning: The 'repr' attribute with value False was provided to the `Field()` function, which has no effect in the context it was used. 'repr' is field-specific metadata, and can only be attached to a model field using `Annotated` metadata or by assignment. This may have happened because an `Annotated` type alias using the `type` statement was used, or if the `Field()` function was attached to a single member of a union type.\n",
       "  warnings.warn(\n",
-      "/home/sharifm/students/matanbentov/my_conda/envs/default/lib/python3.10/site-packages/pydantic/_internal/_generate_schema.py:2249: UnsupportedFieldAttributeWarning: The 'frozen' attribute with value True was provided to the `Field()` function, which has no effect in the context it was used. 'frozen' is field-specific metadata, and can only be attached to a model field using `Annotated` metadata or by assignment. This may have happened because an `Annotated` type alias using the `type` statement was used, or if the `Field()` function was attached to a single member of a union type.\n",
+      ".../site-packages/pydantic/_internal/_generate_schema.py:2249: UnsupportedFieldAttributeWarning: The 'frozen' attribute with value True was provided to the `Field()` function, which has no effect in the context it was used. 'frozen' is field-specific metadata, and can only be attached to a model field using `Annotated` metadata or by assignment. This may have happened because an `Annotated` type alias using the `type` statement was used, or if the `Field()` function was attached to a single member of a union type.\n",
       "  warnings.warn(\n"
      ]
     },
@@ -315,7 +315,7 @@
     "### 2b. Multi-instruction optimization\n",
     "\n",
     "As another variant of the recipe, which is considered to create more _universal_ jailbreak suffix, you can \n",
-    "pass multiple templates to optimize a single trigger against them all of them simultaneously."
+    "pass multiple templates to optimize a single trigger against all of them simultaneously."
    ]
   },
   {
@@ -457,7 +457,7 @@
    ],
    "source": [
     "# Embed multiple Harry Potter queries and average them into a \"concept\" centroid.\n",
-    "# A trigger optimized toward this centroid will steer an attacker-controlled\n",
+    "# A trigger optimized toward this centroid will steer an attacker-controlled passage toward these queries in retrieval.\n",
     "hp_queries = [\n",
     "    \"Who is Harry Potter?\",\n",
     "    \"Tell me about the Harry Potter series.\",\n",
@@ -845,7 +845,7 @@
    ],
    "source": [
     "# Optimize a trigger appended to an off-topic passage so that its\n",
-    "# OpenAI embedding aligns with the embedding of `target_text`.\n",
+    "# OpenAI embedding aligns with the target centroid (`target_vector`).\n",
     "loss = SimilarityLoss()  # minimizes −cosine_similarity → maximizes alignment\n",
     "\n",
     "optimizer = RandomSearchOptimizer(\n",
@@ -875,7 +875,7 @@
     "\n",
     "In TROPT you can also easily customize losses and build new optimizers.\n",
     "\n",
-    "Concretely, to create a new loss, you implement its core computation logic, accepting standardized parameters (resolved from `[ModelInput](https://tropt.dev/api/common.html#tropt.common.ModelInput)`, `[ModelOutput](https://tropt.dev/api/common.html#tropt.common.ModelOutput)`, and `[MessageTargets](https://tropt.dev/api/common.html#tropt.common.MessageTargets)`), with no registration required.\n",
+    "Concretely, to create a new loss, you implement its core computation logic, accepting standardized parameters (resolved from [`ModelInput`](https://tropt.dev/api/common.html#tropt.common.ModelInput), [`ModelOutput`](https://tropt.dev/api/common.html#tropt.common.ModelOutput), and [`MessageTargets`](https://tropt.dev/api/common.html#tropt.common.MessageTargets)), with no registration required.\n",
     "Similarly, implementing a new optimizer requires defining its core search algorithm around a compact interface that connects it to TROPT's framework — fitting it with all compatible models, losses, etc.\n",
     "\n",
     "Below we define both from scratch and run them against an encoder model.\n",